KARTA — spend control for AI agents MCP Server

by rta-karta Your server? Claim it

answering

KARTA — spend control for AI agents is answering right now. Last checked 1 min ago. It exposes 6 tools.

Task envelope, budget ledger, kill switch and signed receipts for agents that pay.

The linked repository no longer exists on GitHub — it was deleted or made private.

Uptime history 6 days of history · worst day 92%

6 days agonow

98.9%

Uptime 24h

91 of 92 checks

Tools

read from the server

807 ms

Response time

average over 24h

open, no key

Access

streamable-http

What changed 5

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 27 October 2026. No other catalogue keeps this.

27 Oct 5 tools appeared envelope_evidence, get_envelope, kill_envelope and 2 more

KARTA — spend control for AI agents does not always answer

Over the last week it answered 97.6% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 1 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add guard --transport http https://karta.rta.lat/mcp

Settings → Connectors → Add custom connector, then paste this address

https://karta.rta.lat/mcp

~/.codex/config.toml

[mcp_servers.guard]
url = "https://karta.rta.lat/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "guard": {
      "url": "https://karta.rta.lat/mcp"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "guard": {
      "type": "http",
      "url": "https://karta.rta.lat/mcp"
    }
  }
}

Available tools 6

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

envelope

envelope_evidence

Return an evidence bundle for one envelope: state, every recorded spend, the stop record and a sha256 of the whole pack that anyone can recompute. Read-only.

get_envelope

Return an envelope's state: budget, per-call cap, calls used, spent, remaining, allowlist and expiry. Read-only.

kill

kill_envelope

Stop one task envelope immediately: no further spend is approved for it, the reason is recorded with a timestamp. Idempotent — the first reason wins.

open

open_envelope

Create a signed budget envelope for one task: total budget, per-call cap, call count, allowlisted payees, subscription rule, expiry. Stores it in this server's local ledger (no funds move, no keys). Returns the envelope id. Capped at 30 envelopes/hour per server.

policy

policy_rules

List the deterministic rules a spend is checked against (E01-E08) with the order they are applied and the meaning of each. Read-only, no state.

spend

check_spend

Check whether a proposed agent spend is inside a task envelope. Returns verdict, rule, reason, counterfactual and next. No state is stored.

Endpoints

URL	Transport	State	Latency	Checked
https://karta.rta.lat/mcp	streamable-http	answering	768 ms	1 min ago

Alternatives to KARTA — spend control for AI agents

same job, measured the same way

AgentGuard

by merchantguard

Local spend caps, kill-switch blocking and Ed25519-signed receipts for AI agent tool calls.

71 installs/wk local only

Regent Protocol

by regentprotocol

Spending control for AI agents: approved budgets, a decision before each payment, signed receipts.

answering

AgentiSend

by fortuneflick

Email API for apps and AI agents: budgets per key, a kill switch, refusals that name the fix.

45 installs/wk answering

Silvanexum

by silvanexum

Spend control for AI agents - cost attribution, budget caps, and signed runs as MCP tools.

234 installs/wk local only

Gvnr

by gvnr

Budget & cost control for AI agents — per-agent spend caps + rate limits before each call.

answering

Countersign

by countersign-network

Kill switch + spend guard for AI agents that spend money, across every wallet vendor at once.

76 installs/wk local only

Tabularium

by sqlazy

Agent memory and a signed spending ledger: pay any x402 API, keep a provable receipt.

2 132 installs/wk local only

Agent Wallet

by dingdawg

Governed USDC wallet for AI agents — policy gates, spending caps, and Ed25519-signed receipts.

105 installs/wk local only

KARTA — spend control for AI agents — questions

Answers built from our own checks of this server.

What can KARTA — spend control for AI agents do?

It exposes 6 tools, read directly from the server on our last check. Among them: check_spend, envelope_evidence, get_envelope, kill_envelope, open_envelope, policy_rules. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is KARTA — spend control for AI agents working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 92 checks got a reply (98.9%), average response time 807 ms. The bar chart above shows every period we have measured.

Is KARTA — spend control for AI agents still maintained?

The linked repository no longer exists on GitHub — it was deleted or made private. We show this because it changes what you can expect: an unmaintained server may keep answering for months and then stop without warning.

How do I connect KARTA — spend control for AI agents?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does KARTA — spend control for AI agents need an API key?

No. KARTA — spend control for AI agents completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 6 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is KARTA — spend control for AI agents?

It answers our handshake in 807 ms on average, which is faster than 10% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.